RepoAlerts

FutureMLS-Lab/FlashStates

App

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 7 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 6 days ago.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Inference serving for hybrid attention models (attention plus linear-attention or state-space layers) that reuses cached prefixes for coding-agent sessions. It saves recurrent checkpoints at any token position and manages hybrid state with a cost-aware eviction policy, with an…

Who it's for

ML engineers serving hybrid LLMs with agentic, multi-turn workloads on vLLM

How to use it

Ready-made installers, when the project publishes them, are on its latest release.

Downloads (if any)

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up FutureMLS-Lab/FlashStates in my project. Follow its README: https://github.com/FutureMLS-Lab/FlashStates. Explain each step and check it is safe before running anything.

Read the README

Star curve

240From 34 to 240 stars between 9 Nov 2026 and 16 Nov 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![FutureMLS-Lab/FlashStates on RepoAlerts](https://repoalerts.com/badge/FutureMLS-Lab/FlashStates.svg)](https://repoalerts.com/repo/FutureMLS-Lab/FlashStates?ref=badge)
Share on X

  • FlashML-org/FreeToken

    Edge-native Mixture-of-Experts serving engine for running large open-weight MoE models on consumer hardware. It combines CPU and GPU execution, expert caching and KV cache management, and exposes Anth

    AppModels & inferencePython · 17,234 stars · +373 this week · 119 days old

  • snap-stanford/memorilla

    Research code for Memorilla, a memory system that compresses an entire document collection into a fixed set of 16 query-dependent memory tokens fed to a frozen LLM. It includes training recipes, evalu

    ModelModels & inferencePython · 1,268 stars · +515 this week · 147 days old

  • basetenlabs/deepseek-ultrafast

    An inference engine for DeepSeek-V4.1-Flash on NVIDIA sm_100a and sm_103a GPUs, with 1M-token context and KV cache sharing across servers over RDMA, coordinated through Redis. Includes an OpenAI-compa

    AppModels & inferenceRust · 448 stars · +448 this week · 21 days old · HN 71 pts

  • Aevonix/FlashAlign

    Applies alignment profiles per request to models served through an inference engine, using abliteration for approved users and channels or keeping a profile active on all routed requests. Works with s

    AppModels & inferencePython · 126 stars · +1 this week · 17 days old

  • apple-aiml-research/ml-rsi-inference-bench

    A long-horizon benchmark for coding agents that improve the inference stack of large language models in vLLM or SGLang. Tasks cover supporting a model on day 0, optimizing it after launch, and repairi

    AI agentsPython · 166 stars · +26 this week · 31 days old

  • Picom-code/pico-dgx-ds4

    A fork of blaesus/dsgx10 that serves DeepSeek V4.1 Flash across four DGX Spark machines for many concurrent users. It adds sparse-attention changes for 1M context, slot admission by context size, spec

    Models & inferenceCuda · 118 stars · +92 this week · 11 days old